© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16730
    Prev
    Next
    INDEX
    Explanations

    rendering ImageView or any rendering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    好象
    -0.10
    éĿŀåħ¸
    -0.09
    èĥ¡éĶ¦æ¶Ľ
    -0.09
     idéia
    -0.09
    就象
    -0.09
    èĭ±æĸĩåIJįåŃĹ
    -0.08
    å¸ĥä»Ģ
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    æĸ°ä¸ĸ纪
    -0.08
    æĥŁä¸Ģ
    -0.08
    POSITIVE LOGITS
    é¢ĦåĪ¤
    0.11
    大æ¦Ĥçİĩ
    0.11
    èµĭèĥ½
    0.11
    åįłæ¯Ķ
    0.11
    ä¸Ģä¼Ĺ
    0.10
    ç²¾åĩĨ
    0.10
    å®ŀæĵį
    0.10
    åĨľä¸ļåĨľæĿijéĥ¨
    0.10
    缸æ¯Ķäºİ
    0.10
    大æķ°æį®
    0.09
    Activations Density 0.001%

    No Known Activations